Add FR translation for R-messages (#19)

* add FR message translation

* wrap cli_abort for translation

* add test

* add NEWS

* fix typos

DESCRIPTION

@@ -3,6 +3,7 @@ Title: Fast Text Tokenization
 Version: 0.1.4.9000
 Authors@R: c(
     person("Daniel", "Falbel", , "daniel@posit.co", c("aut", "cre")),
+    person("Regouby", "Christophe", , "christophe.regouby@free.fr", c("ctb")),
     person(family = "Posit", role = c("cph"))
   )
 Description:
@@ -14,7 +15,7 @@ License: MIT + file LICENSE
 SystemRequirements: Rust tool chain w/ cargo, libclang/llvm-config
 Encoding: UTF-8
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.3.1
+RoxygenNote: 7.3.2
 Depends:
     R (>= 4.2.0)
 Imports:

NEWS.md

@@ -1,5 +1,7 @@
 # tok (development version)
 
+- add message translation in FR (#19, @cregouby)
+
 # tok 0.1.4
 
 - Updated libR-sys to fix mac oldrel notes. (#18)

R/encoding.R

@@ -26,7 +26,7 @@ encoding <- R6::R6Class(
       if (inherits(encoding, "REncoding")) {
         self$.encoding <- encoding
       } else {
-        cli::cli_abort("Expected class {.cls REncoding} but got {.cls {class(encoding)}}.")
+        cli::cli_abort(gettext("Expected class {.cls REncoding} but got {.cls {class(encoding)}}."))
       }
     }  
   ),

R/tokenizer.R

@@ -83,7 +83,7 @@ tokenizer <- R6::R6Class(
     #' the tokenizer.
     #' @param path Path to tokenizer.json file
     from_file = function(path) {
-      cli::cli_abort("This is a static method. Not available for tokenizers instances.")
+      cli::cli_abort(gettext("This is a static method. Not available for tokenizers instances."))
     },
 
     #' @description 
@@ -94,7 +94,7 @@ tokenizer <- R6::R6Class(
     #' @param auth_token An optional auth token used to access private repositories 
     #'    on the Hugging Face Hub
     from_pretrained = function(identifier, revision = "main", auth_token = NULL) {
-      cli::cli_abort("This is a static method. Not available for tokenizers instances.")
+      cli::cli_abort(gettext("This is a static method. Not available for tokenizers instances."))
     },
 
     #' @description
@@ -104,7 +104,7 @@ tokenizer <- R6::R6Class(
     #' @param files character vector of file paths.
     train = function(files, trainer) {
       if (!inherits(trainer, "tok_trainer"))
-        cli::cli_abort("{.arg trainer} must inherit from {.cls tok_trainer}.")
+        cli::cli_abort(gettext("{.arg trainer} must inherit from {.cls tok_trainer}."))
 
       self$.tokenizer$train_from_files(trainer$.trainer, normalizePath(files))
     },
@@ -227,15 +227,15 @@ tokenizer <- R6::R6Class(
     #' @field padding Gets padding configuration
     padding = function(x) {
       if (!missing(x)) {
-        cli::cli_abort("Can't be set this way, use {.fn enable_padding}.")
+        cli::cli_abort(gettext("Can't be set this way, use {.fn enable_padding}."))
       }
 
       self$.tokenizer$get_padding()
     },
     #' @field truncation Gets truncation configuration
     truncation = function(x) {
       if (!missing(x)) {
-        cli::cli_abort("Can't be set this way, use {.fn enable_truncation}.")
+        cli::cli_abort(gettext("Can't be set this way, use {.fn enable_truncation}."))
       }
 
       self$.tokenizer$get_truncation()

po/R-fr.po

@@ -0,0 +1,32 @@
+msgid ""
+msgstr ""
+"Project-Id-Version: tok 0.1.4.9000\n"
+"POT-Creation-Date: 2024-09-04 19:29+0200\n"
+"PO-Revision-Date: 2024-09-04 19:39+0200\n"
+"Last-Translator: \n"
+"Language-Team: \n"
+"Language: fr\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=UTF-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"X-Generator: Poedit 3.4.3\n"
+
+#: encoding.R:29
+msgid "Expected class {.cls REncoding} but got {.cls {class(encoding)}}."
+msgstr "Classe attendue {.cls REncoding}. Ici la classe est {.cls {class(encoding)}}."
+
+#: tokenizer.R:86 tokenizer.R:97
+msgid "This is a static method. Not available for tokenizers instances."
+msgstr "Il s'agit d'une méthode statique. Elle n'est pas disponible pour les instances de tokenizers."
+
+#: tokenizer.R:107
+msgid "{.arg trainer} must inherit from {.cls tok_trainer}."
+msgstr "{.arg trainer} doit hériter de {.cls tok_trainer}."
+
+#: tokenizer.R:230
+msgid "Can't be set this way, use {.fn enable_padding}."
+msgstr "Ne peut pas être défini de cette manière, vous devez utilisez {.fn enable_padding}."
+
+#: tokenizer.R:238
+msgid "Can't be set this way, use {.fn enable_truncation}."
+msgstr "Ne peut pas être défini de cette manière, vous devez utilisez {.fn enable_truncation}."

po/R-tok.pot

@@ -0,0 +1,31 @@
+msgid ""
+msgstr ""
+"Project-Id-Version: tok 0.1.4.9000\n"
+"POT-Creation-Date: 2024-09-04 19:29+0200\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language-Team: LANGUAGE <LL@li.org>\n"
+"Language: \n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=UTF-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+
+#: encoding.R:29
+msgid "Expected class {.cls REncoding} but got {.cls {class(encoding)}}."
+msgstr ""
+
+#: tokenizer.R:86 tokenizer.R:97
+msgid "This is a static method. Not available for tokenizers instances."
+msgstr ""
+
+#: tokenizer.R:107
+msgid "{.arg trainer} must inherit from {.cls tok_trainer}."
+msgstr ""
+
+#: tokenizer.R:230
+msgid "Can't be set this way, use {.fn enable_padding}."
+msgstr ""
+
+#: tokenizer.R:238
+msgid "Can't be set this way, use {.fn enable_truncation}."
+msgstr ""

tests/testthat/test-message-translations.R

@@ -0,0 +1,15 @@
+test_that("R-level cli_abort messages are correctly translated in FR", {
+  withr::with_envvar(c(HUGGINGFACE_HUB_CACHE = tempdir()), {
+    try({
+      tok <- tokenizer$from_pretrained("gpt2")
+      temp_json <- tempfile(fileext = ".json")
+      withr::with_language(lang = "fr",
+                           expect_error(
+                             tok$train(temp_json, temp_json),
+                             regexp = "doit hériter de",
+                             fixed = TRUE
+                           ))
+    })
+  })
+
+})